cs.CL

Papers

• Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference (2026)
  Sangyun Lee et al.
  15.03
• MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research (2026)
  Dingbang Wu et al.
  14.25
• Rethinking Memory as Continuously Evolving Connectivity (2026)
  Jizhan Fang et al.
  13.31
• Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling (2026)
  Xinglin Wang et al.
  13.12
• GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection (2026)
  Zheng Wu et al.
  12.92
• Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning (2026)
  Jiapeng Zhu et al.
  12.46
• OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration (2026)
  Xinchen Zhang et al.
  11.20
• Coding Speech through Vocal Tract Kinematics (2025)
  Cheol Jun Cho et al.
  11.19
• QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents (2026)
  Ye Yuan et al.
  10.67
• Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders (2026)
  Yi Jing et al.
  10.61
• Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement (2026)
  Dingwei Chen et al.
  10.27
• ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence (2026)
  Rui Meng et al.
  10.05
• Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems (2026)
  Bingyu Yan et al.
  9.75
• MobileMoE: Scaling On-Device Mixture of Experts (2026)
  Yanbei Chen et al.
  9.24
• Models That Know How Evaluations Are Designed Score Safer (2026)
  Katharina Deckenbach et al.
  9.04
• Multi-Agent Causal Discovery Using Large Language Models (2026)
  Hao Duong Le et al.
  7.59
• Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization (2026)
  Anmol Agarwal et al.
  6.98
• Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models (2026)
  Yifan Jiang et al.
  6.98
• CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations (2026)
  Mike Zhang et al.
  6.17
• SIA: Self Improving AI with Harness & Weight Updates (2026)
  Prannay Hebbar et al.
  5.68
• Real-time Speech Summarization for Medical Conversations (2025)
  Khai Le-Duc et al.
  5.24
• Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions (2026)
  Antonia Karamolegkou et al.
  5.06
• Advancing Creative Physical Intelligence in Large Multimodal Models (2026)
  Cheng Qian et al.
  5.04
• Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases (2026)
  Dongyoon Hahm et al.
  5.04
• DEPART: DEcomposing PARiTy across Multilingual LLMs (2026)
  Manan Uppadhyay et al.
  4.54
• Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment (2026)
  Seojin Hwang et al.
  4.54
• Pruning and Distilling Mixture-of-Experts into Dense Language Models (2026)
  Junhyuck Kim et al.
  4.54
• When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR (2026)
  Maike Z\"ufle et al.
  4.54
• Analyzing Quality-Latency-Resource Trade-offs in a Technical Documentation RAG Assistant Using LoRA Adaptation (2026)
  Evgenii Palnikov et al.
  4.54
• Why We Need Speech to Evaluate Speech Translation (2026)
  Maike Z\"ufle et al.
  4.54
• PrunePath: Towards Highly Structured Sparse Language Models (2026)
  Zhexuan Gu et al.
  4.54
• Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning (2026)
  Yahan Yu et al.
  4.54
• Routing-Aligned Fine-Tuning for Multilingual Downstream Tasks in Mixture-of-Experts Models (2026)
  Guanzhi Deng et al.
  4.54
• PubMedCausal: A Span-Level Annotated Corpus for Causal Relation Extraction in Biomedical Text (2026)
  Ifeoluwa Kunle-John et al.
  4.54
• FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning (2026)
  Haihui Pan et al.
  4.54
• Breaking the Script Barrier: Enabling Automatic Alignment for PoS-based ASR Error Analysis in Non-Latin Scripts (2026)
  Prasenjit K Mudi et al.
  4.54
• AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates (2026)
  Shaolong Chen et al.
  4.54
• The Cases LJP Never Sees: Prosecution Decision Prediction for More Complete Criminal Liability Assessment (2026)
  Junyu Lu et al.
  4.54
• Soft-SVeRL: Self-Verified Reinforcement Learning with Soft Rewards (2026)
  Saurabh Dash et al.
  4.54
• Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News (2026)
  Alejandro Buitrago L\'opez et al.
  4.54
• Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents (2026)
  Zheng Wu et al.
  4.54
• Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study (2026)
  Irune Zubiaga et al.
  4.54
• IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents (2026)
  Michael Galarnyk et al.
  4.54
• The Abstraction Gap in Vision-Language Causal Reasoning (2026)
  Chinh Hoang et al.
  4.54
• Skill-Conditioned Gated Self-Distillation for LLM Reasoning (2026)
  Jiazhen Huang et al.
  4.54
• Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization (2026)
  Beiduo Chen et al.
  4.54
• VLMs May Not Globally Enhance Human Alignment over LLMs During Natural Reading (2026)
  Jinzhou Wu et al.
  4.54
• Finding Pareto Trade-offs in Fair and Accurate Detection of Toxic Speech (2025)
  Soumyajit Gupta et al.
  4.52
• AgentAtlas: Beyond Outcome Leaderboards for LLM Agents (2026)
  Parsa Mazaheri et al.
  3.91
• MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation (2026)
  Szu-Chi Chen et al.
  3.87